Leaderboard de benchmarks de IA
Cada puntuacion, cada fuente.
Datos de benchmarks desde fuentes oficiales para modelos frontera. La vista actual oculta modelos reemplazados y versiones antiguas. El archivo conserva el historial.
Ultima actualizacion2026-10-03
Modelos mostrados36
Benchmarks mostrados19
| Modelo | Proveedor | Entrada $/M | Salida $/M | SWE-bench Pro | Terminal-Bench 2.1 | Terminal-Bench 3.0 | DeepSWE 1.1 | MCP-Atlas | Toolathlon | AutomationBench | OSWorld-Verified | BrowseComp | GPQA Diamond | AA Intelligence Index | Humanity's Last Exam | Humanity's Last Exam with tools | FrontierMath T1-3 (v2) | ARC-AGI-2 | ARC-AGI-3 | Finance Agent v2 | GDPval-AA v2 | CyberGym |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
GPT-6.1 Sol ChatGPT Work, Codex and API; not Chat mode at launch. Pro is an execution mode, not a separate model. No verified benchmark scores added. | OpenAI | $2.00 | $10.00 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
Claude Fable 5.1 | Anthropic | $10.00 | $50.00 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | ||||
Claude Opus 5 | Anthropic | $5.00 | $25.00 | - | - | - | - | - | - | - | - | - | - | |||||||||
Claude Opus 5.5 | Anthropic | $4.00 | $20.00 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
GPT-5.6 Sol | OpenAI | $4.00 | $20.00 | - | - | - | - | - | - | - | - | - | - | |||||||||
GPT-5.6 Terra | OpenAI | $2.00 | $12.00 | - | - | - | - | - | - | - | - | - | - | |||||||||
GPT-5.6 Luna | OpenAI | $0.20 | $1.20 | - | - | - | - | - | - | - | - | - | - | |||||||||
GPT-6 Astra API live; organization admins may need to enable it | OpenAI | $10.00 | $50.00 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
GPT-6 Sol API; ChatGPT Work and Codex on Plus, Pro, Business, Enterprise, and Edu | OpenAI | $2.00 | $10.00 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
GPT-6 Luna API; ChatGPT paid plans, plus Free and Go users in the ChatGPT desktop app | OpenAI | $0.10 | $0.50 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
Kimi K3 | Moonshot AI | ¥20.00 | ¥100.00 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | |||
Grok 4.7 | xAI | $2.00 | $6.00 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
GLM-5.2 | Z.ai | $1.40 | $4.40 | - | - | - | - | - | - | - | - | - | - | - | ||||||||
GLM-5.3 Available through GLM Coding Plan; public API and API pricing are coming soon. | Z.ai | — | — | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
Gemini 3.6 Flash | $1.50 | $7.50 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | |||||
GLM-5.3-Flash | Z.ai | $0.15 | $0.50 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | |||||
Gemini 3.8 Flash Introductory API price through 2026-12-31 | $0.75 | $3.75 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | |
Gemini 3.5 Flash | $1.50 | $9.00 | - | - | - | - | - | - | - | - | - | |||||||||||
Muse Spark 1.1 | Meta | $1.25 | $4.25 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | |
Qwen3.7-Max | Alibaba | $2.50 | $7.50 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | |
Qwen3.8-Max | Alibaba Cloud | $2.00 | $6.00 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
Qwen3.8-Flash | Alibaba Cloud | $0.11 | $0.38 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
Qwen3.8-27B | Alibaba Cloud | $0.50 | $3.00 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
Qwen 3.8 27B (Groq) Preview on Groq with free-plan rate limits. | Alibaba / Groq | $0.80 | $4.00 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
Gemini 3.5 Flash-Lite | $0.30 | $2.50 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | |||||
GPT-5.5 Pro | OpenAI | $30.00 | $180.00 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | |
GPT-5.4 | OpenAI | $2.50 | $15.00 | - | - | - | - | - | - | - | - | - | - | - | ||||||||
Gemini 3.1 Pro | $2.00 | $12.00 | - | - | - | - | ||||||||||||||||
DeepSeek V4 Pro V4-Pro-0813 remains available as deepseek-v4-pro; the proposed retirement was reversed. | DeepSeek | $1.32 | $3.96 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
Grok 4.3 | xAI | $1.25 | $2.50 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
GPT-OSS 120B | OpenAI via Groq | $0.15 | $0.60 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
Kimi K2.6 | Moonshot AI | ¥1.10 | ¥27.00 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
Kimi K2.7-Code | Moonshot AI | ¥1.30 | ¥27.00 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | |
MiniMax M3 | MiniMax | $0.30 | $1.20 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | |||
DeepSeek V4.1 Flash Use deepseek-flash. Old Flash and Vision Exp aliases route here; do not treat them as separate current models. Historical V4 Flash benchmark scores are not transferred. | DeepSeek | $0.30 | $1.20 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
Claude Sonnet 5.5 Current API model; no previous Sonnet benchmark scores copied. | Anthropic | $2.00 | $10.00 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
URL de fuente oficial
Fuente oficial comparativa
Las celdas vacias significan que no encontramos una fuente oficial. No estimamos.
The Dispatch · Weekly
New scores, in your inbox.
Benchmark refreshes, model launches, and source-checked analysis. One email a week, no noise.
Analisis relacionados
Comparaciones completas basadas en estos datos.